CN117540101B

CN117540101B - Online bookend management method and system based on artificial intelligence

Info

Publication number: CN117540101B
Application number: CN202311643290.7A
Authority: CN
Inventors: 刘朋
Original assignee: Shenzhen Eryi Education Technology Co ltd
Current assignee: Shenzhen Eryi Education Technology Co ltd
Priority date: 2023-12-04
Filing date: 2023-12-04
Publication date: 2024-06-04
Anticipated expiration: 2043-12-04
Also published as: CN117540101A

Abstract

The invention discloses an artificial intelligence-based online book management method and system, comprising the following steps: acquiring user characteristic information, carrying out preference analysis on a target user according to the user characteristic information, and constructing a user preference portrait; acquiring target book information, performing book relevance analysis, and performing personalized learning path recommendation according to analysis results and user preference portraits; acquiring reading condition information of a target book block, and carrying out reading style analysis on the target book block to obtain reading style analysis information; and carrying out reading trend analysis on the target book city according to the reading style analysis information, and carrying out operation strategy formulation. The reading preference of the user can be better met through intelligent recommendation and personalized customization by artificial intelligence. Meanwhile, the real-time data analysis technology enables the bookend to quickly respond to market changes, flexibly adjusts operation strategies and enhances the competitiveness of the target bookend.

Description

Online bookend management method and system based on artificial intelligence

Technical Field

The invention relates to the technical field of online bookend management, in particular to an online bookend management method and system based on artificial intelligence.

Background

In the current era background of rapid development of digitization and informatization, the traditional book city faces new challenges and opportunities. The manner in which users acquire books has fundamentally changed from traditional physical bookstores to online bookends, traditional bookend operations and books face unprecedented challenges and changes. With the popularity of the internet, the manner in which users acquire information and purchase goods has changed fundamentally, including book purchasing and reading habits. Traditional bookends are increasingly under pressure for digital transformation, and more intelligent and personalized management methods are needed to adapt to the changing market environment.

The rise of digital reading and online book purchasing causes the book sales platform to be in charge of the processing and management tasks of mass data. Traditional bookends have difficulty effectively dealing with this complex interaction of huge book inventory, user demand and market trends. In this environment, a method for managing books using artificial intelligence stands out.

Artificial intelligence techniques, such as natural language processing, machine learning, and data mining, provide tools for processing and analyzing mass data for online bookends. Under the condition that the user needs to be increasingly personalized, the reading preference of the user can be better met through the intelligent recommendation system and the personalized service. Meanwhile, the real-time data analysis technology enables books to quickly respond to market changes, inventory and operation strategies are flexibly adjusted, and competitiveness is improved. Therefore, how to better utilize artificial intelligence to more intelligently and efficiently manage online books is a problem to be solved.

Disclosure of Invention

The invention overcomes the defects of the prior art, and provides an on-line bookend management method and system based on artificial intelligence, which are important for better meeting the reading preference of users and efficiently managing the on-line bookends and enhancing the competitiveness of bookends.

In order to achieve the above object, the first aspect of the present invention provides an online bookend management method based on artificial intelligence, including:

acquiring user characteristic information, carrying out preference analysis on a target user according to the user characteristic information, and constructing a user preference portrait;

Acquiring target book information, performing book relevance analysis, and performing personalized learning path recommendation according to analysis results and user preference portraits;

Acquiring reading condition information of a target book block, and carrying out reading style analysis on the target book block to obtain reading style analysis information;

and carrying out reading trend analysis on the target book city according to the reading style analysis information, and carrying out operation strategy formulation.

In this solution, the performing preference analysis on the target user according to the user feature information, and constructing a user preference portrait specifically includes:

Acquiring user characteristic information, wherein the user characteristic information comprises reading characteristics and behavior characteristics of a target user;

carrying out favorite preference analysis according to the user characteristic information, and extracting the reading type, frequency and time characteristics of a target user to obtain first characteristic information;

Presetting attribute categories, carrying out attribute clustering by combining first characteristic information based on a clustering algorithm, and carrying out attribute analysis on the historical reading categories of the target user to obtain attribute analysis information;

Presetting a plurality of preference evaluation thresholds, extracting the reading frequency and time of each attribute category according to the attribute analysis information and the first characteristic information, and judging with the preference evaluation thresholds to obtain preference evaluation result information;

And presetting a selection threshold, sorting according to the preference evaluation result information, and analyzing the reading preference attribute of the target user through the selection threshold to obtain first preference analysis information.

In this solution, the performing preference analysis on the target user according to the user feature information, and constructing a user preference portrait, further includes:

Carrying out attention preference analysis according to the user characteristic information, extracting behavior characteristics of a target user, including click frequency, time, collection, purchase, reading and interaction characteristics, and obtaining second characteristic information;

According to the second characteristic information, the frequency, the category and the residence time of the book clicked by the user are extracted and counted, the click frequency and the residence time are judged with a preset threshold value, and attribute analysis is carried out according to the category of the book clicked, so that judgment result information and analysis result information are respectively obtained;

Setting a concern category according to the analysis result information, carrying out weighted calculation by taking the click frequency and the stay time as concern degree weights in combination with the judgment result information, and carrying out concern preference analysis according to the calculation result to obtain second preference analysis information;

Constructing a user active analysis model, and inputting the second characteristic information and the second preference analysis information into the user active analysis model for analysis to obtain active analysis information;

the first preference analysis information, the second preference analysis information and the activity analysis information are combined to form user preference analysis information, and a user preference portrait is constructed according to the user preference analysis information.

In this scheme, the book association analysis is performed, and personalized reading path recommendation is performed by combining the user preference image according to the analysis result, and specifically includes:

acquiring target book information, reading history information of a book user, real-time reading information of the user and user preference portraits;

Content relevance analysis is carried out according to the target book city book information, manhattan distance among books is calculated, and judgment is carried out with a preset threshold value, so that first relevance analysis information is obtained;

Reading association analysis is carried out according to the reading history information of the book city user, a user reading sequence is constructed through the reading history of the book city user, and the reading books are associated according to the time sequence and the reading sequence through the user reading sequence, so that second association analysis information is obtained;

Counting reading frequency and duration of various historical reading books as relevancy, and constructing a book relevancy graph by combining the first relevancy analysis information and the second relevancy analysis information;

According to a Markov algorithm and a collaborative filtering algorithm, reading book mixed recommendation is carried out, a reading recommendation model is built, real-time reading information of a user and user preference portrait information are input into the reading recommendation model for reading recommendation analysis, and reading recommendation information is obtained;

According to the book association map, carrying out recommendation priority assessment by combining the reading recommendation information, taking the association degree as a priority recommendation assessment index, and carrying out priority assessment on each recommended book to obtain priority assessment information;

and combining the reading recommendation information and the priority evaluation information to make a personalized reading path, and pushing the personalized reading path to a target user to carry out reading recommendation.

In this scheme, the reading recommendation information is obtained by inputting the real-time reading information of the user and the user preference portrait information into the reading recommendation model for reading recommendation analysis, and further comprises:

calculating similar users and similar books of the target bookend according to the real-time reading information of the users and the user preference portraits, and constructing a similar user set and a similar book set;

generating a first recommendation list through the user preference portrait and the book association map based on the collaborative filtering algorithm, extracting the reading frequency of each book in the first recommendation list through the book association map, sorting the books, and constructing a second recommendation list according to the sorting result;

calculating an intersection and a union of the first recommendation list and the second recommendation list to obtain intersection recommendation list information and union recommendation list information;

randomly selecting N similar users from the similar user set according to the real-time reading information of the users, and extracting the subsequent reading books of the similar users through the reading history information of the book city users to form a third recommendation list;

Extracting association degree information of each book according to the third recommendation list and the associated book map, and taking the association degree information as recommendation weight;

Comparing and analyzing the third recommendation list with the union list, if the third recommendation list exists in the union list, reserving the target recommendation books, and if the third recommendation list does not exist in the union list, discarding the target recommendation books;

And forming a fourth recommendation list according to the comparison analysis result and the intersection recommendation list information, carrying out weighted calculation on the fourth recommendation list through recommendation weight, and selecting a final recommended book according to the weighted calculation result to obtain reading recommendation information.

In this scheme, obtain the reading situation information of target book city, read style analysis to target book city, obtain reading style analysis information, specifically include:

Acquiring reading condition information of a target book block and book information of the target book block, extracting characteristics of the book information of the target book block, extracting theme characteristics and content characteristics of the target book block and obtaining book characteristic information;

presetting style categories, carrying out style division on books in a target book city according to book characteristic information based on a clustering algorithm, and classifying corresponding books into the corresponding style categories to obtain book style division information;

analyzing the reading condition of the target book end according to the reading condition information, extracting daily reading quantity, weekly reading quantity and monthly reading quantity of various books, and constructing a reading quantity trend chart;

according to the reading condition information and the book style dividing information, carrying out reading attribute analysis, classifying the reading attributes into three categories of gender, age and region, and analyzing the reading conditions of different reading attributes by combining the reading quantity trend graph to obtain reading condition analysis information;

Based on the reading quantity trend graph and the reading condition analysis information, taking the reading quantity as an evaluation index of the main stream reading style, taking the rising trend of the reading quantity as a potential reading style evaluation index, and respectively carrying out main stream reading style analysis and potential reading style analysis to obtain main stream reading style analysis information and potential reading style analysis information;

and combining the mainstream reading style analysis information and the potential reading style analysis information to form the reading style analysis information.

In this scheme, reading trend analysis is performed on the target bookend according to reading style analysis information, and an operation policy is formulated, which specifically includes:

acquiring reading style analysis information and a reading quantity trend graph, acquiring main stream reading style analysis information according to the reading style analysis information, and carrying out state analysis on the main stream reading style by combining the reading quantity trend graph;

analyzing the difference between the reading quantity of each main stream reading style in the current time period and the reading quantity in the historical time period through the reading quantity trend graph, judging and analyzing the change trend, and calculating the change rate to obtain first analysis information;

Potential reading style analysis information is obtained according to the reading style analysis information, the reading quantity increasing rate and period are used as evaluation indexes, and potential evaluation is carried out on each potential reading style by combining with the reading quantity trend graph;

Presetting a plurality of potential grade evaluation thresholds, calculating the growth rate and period of each potential reading style through a reading quantity trend chart, and judging with the potential grade evaluation thresholds to obtain second analysis information;

Acquiring reading condition information of a target book city, calculating click rate, reading rate and purchasing rate information of each potential reading style by combining the second analysis information, and correlating click-reading-purchasing to form a mapping matrix;

Constructing a reading style operation recommendation model, inputting first analysis information, second analysis information and a mapping matrix into the reading operation recommendation model for analysis, and analyzing operation feasibility and benefit of each style to obtain operation style recommendation information;

Acquiring historical operation strategy information, and performing operation direction analysis on each piece of historical operation strategy information to obtain operation direction analysis information;

And extracting the operation effect of each historical operation strategy as weight, carrying out weighted calculation on the operation direction analysis information, selecting the optimal operation direction according to the weighted calculation, and formulating the operation strategy by combining the operation style recommendation information.

The second aspect of the invention provides an artificial intelligence based online bookend management system, comprising: the system comprises a memory and a processor, wherein the memory contains an artificial intelligence-based online book management method program, and the artificial intelligence-based online book management method program realizes the following steps when being executed by the processor:

Drawings

In order to more clearly illustrate the technical solutions of embodiments or examples of the present invention, the drawings that are required to be used in the embodiments or examples of the present invention will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive efforts for those skilled in the art.

FIG. 1 is a flowchart of an online book management method based on artificial intelligence according to an embodiment of the present invention;

FIG. 2 is a flow chart of a target book operation analysis according to an embodiment of the present invention;

FIG. 3 is a block diagram of an on-line bookend management system based on artificial intelligence according to an embodiment of the present invention;

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.

as shown in fig. 1, the present invention provides an artificial intelligence based on-line book management method flowchart, comprising:

s102, acquiring user characteristic information, carrying out preference analysis on a target user according to the user characteristic information, and constructing a user preference portrait;

Presetting a selection threshold value, sorting according to the preference evaluation result information, and analyzing the reading preference attribute of the target user through the selection threshold value to obtain first preference analysis information;

It should be noted that, first, feature information of a user is obtained, including reading features and behavior features. The reading characteristics cover the reading preference, frequency and time of the target user, and the behavior characteristics comprise clicking, collecting, purchasing, reading and other behaviors of the user.

And then carrying out preference analysis, carrying out attribute clustering by combining the first characteristic information through preset attribute categories and using a clustering algorithm, and carrying out attribute analysis on the historical reading category of the user so as to obtain attribute analysis information. Setting a plurality of preference evaluation thresholds, extracting the reading frequency and time of each attribute category according to the attribute analysis information and the first characteristic information, judging with the preference evaluation thresholds, and finally obtaining preference evaluation result information. And setting a selection threshold value, and obtaining first preference analysis information by sequencing and analyzing preference evaluation result information, so that main preference attributes of a target user in the reading aspect are displayed. Meanwhile, attention preference analysis is carried out, behavior characteristics of a user are extracted, including click frequency, time, collection, purchase, reading and the like, and judgment result information and analysis result information are obtained through analysis of the click frequency and the residence time and are used for determining the reading category of attention of the user. Then, a user activity analysis model is built through a natural language processing technology or a behavior context analysis technology, second characteristic information and second preference analysis information are input into the model for analysis, behavior meanings of the user are analyzed, for example, the activity of a target user in a certain style plate is judged from interactive behaviors and comment behaviors of the user, the activity analysis information is obtained, the preference of the user on a reading platform is more comprehensively known, and the preference of the user on the style is mapped through the behavior of the user in the certain style plate. And finally, forming user preference analysis information by integrating the first preference analysis information, the second preference analysis information and the active analysis information, and constructing a user preference portrait, so that powerful support is provided for personalized recommendation.

S104, acquiring book information of a target book city, performing book relevance analysis, and performing personalized learning path recommendation according to analysis results and user preference portraits;

combining the reading recommendation information and the priority evaluation information to make personalized reading path formulation, and pushing the personalized reading path formulation to a target user to carry out reading recommendation;

the method comprises the steps of inputting the real-time reading information of the user and the user preference portrait information into a reading recommendation model for reading recommendation analysis to obtain reading recommendation information, and further comprising the following steps:

First, a content correlation analysis stage is performed. And performing Manhattan distance calculation on the target book information, and judging with a preset threshold value to obtain first relevance analysis information. The method is helpful for understanding the content correlation among books and providing preliminary association information for recommendation. Next, a reading association analysis is performed. And constructing a user reading sequence through reading histories of the book users, and performing relevance analysis according to time and reading sequence to obtain second relevance analysis information, so that time sequence relevance of reading behaviors of the users can be captured. After the correlation analysis, counting the reading frequency and duration of various historical reading books, and constructing a book correlation map by combining the first correlation analysis information and the second correlation analysis information. And then, carrying out mixed recommendation of the reading books by combining a Markov algorithm with a collaborative filtering algorithm, and constructing a reading recommendation model. And inputting the real-time reading information of the user and the user preference portrait information into a reading recommendation model to obtain reading recommendation information. And then, in the recommendation stage, carrying out recommendation priority assessment according to the book association map and reading recommendation information. And taking the association degree as a priority recommendation evaluation index, and performing priority evaluation on each recommended book to obtain priority evaluation information. And finally, combining the reading recommendation information and the priority evaluation information to make a personalized reading path, pushing the personalized reading path to a target user to carry out reading recommendation, and providing more personalized and intelligent reading recommendation service for the user.

S106, reading condition information of the target book block is obtained, reading style analysis is carried out on the target book block, and reading style analysis information is obtained;

It should be noted that, first, style categories are preset, and a clustering algorithm is applied to analyze book characteristic information, so as to realize style division of a target book city book. The book style division information is obtained, so that the understanding of the styles of books in a target book block is facilitated, and support is provided for subsequent analysis. And then, comprehensively analyzing according to the reading condition information, and extracting daily reading quantity, weekly reading quantity and monthly reading quantity of various books to form a reading quantity trend chart. Helping to better understand the reading behavior of the user on different books. Then, on the basis of the reading condition information and the book style division information, reading attribute analysis is performed, and the reading attribute is classified into three categories of gender, age and region. By combining the reading quantity trend graph, the reading condition of different reading attributes on books is deeply analyzed, and reading condition analysis information is obtained. And then, taking the reading quantity as an evaluation index of the main stream reading style, taking the rising trend of the reading quantity as an evaluation index of the potential reading style, and carrying out main stream reading style analysis and potential reading style analysis to obtain main stream reading style analysis information and potential reading style analysis information. And finally, combining the main stream reading style analysis information and the potential reading style analysis information to form comprehensive reading style analysis information. A deep understanding about the reading trend and the potential style of the user is provided for the target bookend, and powerful support is provided for formulating corresponding operation strategies.

It should be noted that, the main stream reading style analysis information aims to reveal which reading styles are mainly favored by the current user, that is, which books perform better in terms of reading amount, and are popular with the user. This helps the bookend to better understand the type of books currently popular for more targeted promotion and operation. Potential reading style analysis information focuses on book types that are growing in reading volume, indicating that these styles may become mainstream in the future. Through the analysis, the potential emerging interests of the user can be obtained in advance, and a basis is provided for timely introducing related books and promoting the development of the emerging styles.

S108, carrying out reading trend analysis on the target bookend according to the reading style analysis information, and carrying out operation strategy formulation;

It should be noted that, first, the main stream reading style analysis information is obtained by using the reading style analysis information, and the state analysis is performed by combining with the reading amount trend chart, so as to help to understand the reading condition of the main stream reading style in the current time period. And then, analyzing the difference between the reading quantity of each main stream reading style in the current time period and the reading quantity of each main stream reading style in the historical time period, calculating the change rate, obtaining first analysis information, and revealing the change trend and the change rate of the main stream reading styles. And then, using the reading style analysis information to obtain potential reading style analysis information, setting a potential grade evaluation threshold value, calculating the growth rate and period of each potential reading style through a reading quantity trend graph, and obtaining second analysis information. Thereby highlighting the potential level of the potential reading style and helping to identify the development trend of the potential reading style. And then, acquiring reading condition information of a target book city, and calculating click rate, reading rate and purchasing rate of each potential reading style by combining the second analysis information to form a mapping matrix. User behavior data are further associated, and references are provided for evaluating the operation feasibility and benefit of the potential reading style. And then, constructing a reading style operation recommendation model, analyzing the first analysis information, the second analysis information and the mapping matrix input model, analyzing the operation feasibility and the benefit of each style, recommending, and providing suggestions of which reading styles are operated for a target book city. Finally, the historical operation strategy information is obtained, operation direction analysis is carried out on the historical operation strategy information, and operation attributes in the historical operation strategy, such as preferential, giving or increasing recommendation frequency, are analyzed to obtain operation direction analysis information. And finally, extracting the operation effect of the historical operation strategy as weight, carrying out weighted calculation on the operation direction analysis information, selecting the optimal operation direction, and formulating the optimal operation strategy by combining the operation style recommendation information. By analyzing the operation effect of each operation strategy, the operation direction which better accords with the preference of the user can be found and is close to the preference of the user, so that the operation effect is improved, more benefits are brought, and the competitiveness of the bookend is enhanced.

as shown in fig. 2, the present invention provides a target bookend operation analysis flow chart, including:

S202, analyzing the reading styles of a target book city, analyzing the trend of various reading styles, and analyzing the potential reading styles and the main stream reading styles to obtain reading style analysis information;

S204, analyzing whether the variation trend of the main stream reading style is a sliding trend or a stable trend or an ascending trend;

s206, taking the reading quantity increasing rate and period as evaluation indexes, and performing potential grade evaluation on the potential reading style;

S208, calculating click rate, reading rate and purchasing rate information of each potential reading style, and correlating click-reading-purchasing to form a mapping matrix;

S210, analyzing operation feasibility and benefit of each style through a style operation recommendation model to obtain operation style recommendation information;

S212, selecting an optimal operation direction, and formulating an operation strategy by combining operation style recommendation information.

Further, acquiring historical purchase information of a user, extracting features of the historical purchase information of the user, and extracting features of purchased books and operating strategy features to obtain historical purchase feature information; acquiring user preference portraits of target users, carrying out purchase influence analysis by combining the historical purchase characteristic information, and analyzing whether the purchase behaviors are preference or not to obtain first purchase influence analysis information; performing operation policy influence analysis according to the historical purchase characteristic information, and analyzing whether the operation policy is the purchase behavior performed by the operation policy or not to obtain second purchase influence analysis information; click behavior information before purchasing of a user is extracted according to the historical purchase information of the user, correlation with purchasing behavior is analyzed through the click behavior information, click frequency of successful purchase is counted and correlated with purchasing behavior, and purchasing behavior correlation analysis information is obtained; setting a purchase intention judging rule according to the purchase behavior association analysis information, acquiring real-time book click information of a user, analyzing with the purchase intention judging rule, evaluating the purchase intention degree of the user, and acquiring purchase intention degree information; constructing a purchase prediction model, and inputting the first purchase influence analysis information, the second purchase influence analysis information and the purchase willingness degree information into the purchase prediction model for prediction to obtain purchase prediction result information; and carrying out book recommendation operation according to the purchase prediction result information, and improving the book recommendation frequency, thereby improving the purchase probability of users.

FIG. 3 is a block diagram 3 of an on-line bookend management system based on artificial intelligence according to an embodiment of the present invention, the system includes: the device comprises a memory 31 and a processor 32, wherein the memory 31 contains an artificial intelligence-based online book management method program, and the artificial intelligence-based online book management method program realizes the following steps when being executed by the processor 32:

The invention provides an artificial intelligence-based online book management method and system, which are used for analyzing from the angles of users and books, analyzing the preferences, reading habits and interests of the users and constructing user preference portraits. And then, carrying out relevance analysis on book resources in the bookend, analyzing the relevance between books from the content angle and the reading angle, understanding the relevance between the last book to be read and the next book to be read of the user, possibly based on other characteristics such as theme, content or preference, and the like, combining with user preference images, and implementing personalized learning path recommendation, so that the user can find books which meet the interests of the user more easily. And then, carrying out reading style analysis, analyzing the main stream reading style of the whole bookend, and analyzing the potential reading style in the bookend, thereby revealing the reading preference and trend of the reader group of the target bookend. Based on the reading style analysis information, reading trend analysis is carried out, and the development trend of reading behaviors is analyzed, wherein the development trend comprises rising and declining of different reading styles. So as to understand the needs and market trends of the reader. Finally, an operation strategy is formulated by using the analysis result, so as to optimize the operation of the target bookend, improve the satisfaction degree of users and the economic benefits of the bookend, promote more users to read books in the target bookend, and improve the competitiveness of the target bookend.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.

Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An artificial intelligence based online bookend management method is characterized by comprising the following steps:

according to the reading style analysis information, carrying out reading trend analysis on the target book city, and carrying out operation strategy formulation;

The book relevance analysis is carried out, and personalized learning path recommendation is carried out according to analysis results and by combining user preference portraits, and the method specifically comprises the following steps:

Combining the reading recommendation information and the priority evaluation information to make personalized learning path formulation, and pushing the personalized learning path formulation to a target user for recommendation;

2. The online bookend management method of claim 1, wherein the analyzing the preferences of the target user according to the user characteristic information and constructing the user preference portrait specifically comprises:

3. The online bookend management method of claim 1, wherein said analyzing the preferences of the target user according to the user characteristic information and constructing the user preference portrait further comprises:

4. The method for managing books on line based on artificial intelligence according to claim 1, wherein the steps of obtaining reading status information of a target book, and performing reading style analysis on the target book to obtain reading style analysis information comprise:

5. The online bookend management method of claim 1, wherein the analyzing the reading trend of the target bookend according to the reading style analysis information and making the operation policy specifically comprises:

6. An artificial intelligence based online bookend management system, comprising: the system comprises a memory and a processor, wherein the memory contains an artificial intelligence-based online book management method program, and the artificial intelligence-based online book management method program realizes the following steps when being executed by the processor:

7. The system for managing books on line based on artificial intelligence according to claim 6, wherein the obtaining the reading status information of the target book, and performing reading style analysis on the target book to obtain reading style analysis information, specifically comprises:

8. The online bookend management system of claim 6, wherein the analyzing the reading trend of the target bookend according to the reading style analysis information and making the operation policy specifically comprises: